© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107529
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹³å®ī
    -0.29
    åĤħ
    -0.28
    è¿IJ
    -0.28
    çİ°ä»»
    -0.27
    çIJĨ
    -0.27
    tg
    -0.27
    æ³Ľ
    -0.26
    جب
    -0.26
    æ±īè¯Ń
    -0.26
    åħ«
    -0.26
    POSITIVE LOGITS
    åIJĦè¡ĮåIJĦ
    0.27
     än
    0.26
     ===
    0.26
    etics
    0.26
    .metamodel
    0.25
    kea
    0.25
    Mui
    0.25
    utherland
    0.25
    .isnan
    0.24
    _cmos
    0.24
    Activations Density 11.226%

    No Known Activations

    This feature has no known activations.